Hugging Face's logo

FlagRelease
/
Qwen3-30B-A3B-FlagOS-nvidia

Model card Files Community
YummyYum commited on
Commit
a2726c4
·
verified ·
1 Parent(s): 3469a64

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -4
README.md CHANGED
@@ -42,12 +42,12 @@ We use a variety of Triton-implemented operation kernels to run the Qwen3-30B-A
42
 
43
  | Metrics | Qwen3-30B-A3B-H100-CUDA | Qwen3-30B-A3B-FlagOS-nvidia |
44
  |-------------------|--------------------------|-----------------------------|
45
- | LIVEBENCH | 0.575| 0.565 |
46
  | AIME | 0.800 | 0.833 |
47
  | GPQA | 0.571 | 0.578 |
48
- | MMLU | 0.669 | 0.672 |
49
- | MUSR | 0.648 | 0.637 |
50
- | TheoremQA | 0.121 | 0.118 |
51
 
52
 
53
  # How to Run Locally
 
42
 
43
  | Metrics | Qwen3-30B-A3B-H100-CUDA | Qwen3-30B-A3B-FlagOS-nvidia |
44
  |-------------------|--------------------------|-----------------------------|
45
+ | LIVEBENCH | 0.575| 0.566 |
46
  | AIME | 0.800 | 0.833 |
47
  | GPQA | 0.571 | 0.578 |
48
+ | MMLU | 0.669 | 0.673 |
49
+ | MUSR | 0.648 | 0.638 |
50
+ | TheoremQA | 0.121 | 0.119 |
51
 
52
 
53
  # How to Run Locally